Best suited for
- 01
Routing and triage
Classify intents and route work using probability thresholds.
- 02
Agent evaluation
Judge runs, tool choice and which agent needs attention.
- 03
Policy and scoring
Run moderation, security checks and ordered severity scores.
Benchmarks
Prism leads Sarvam’s 25-model decision study on average score and Indian-language coverage.
Sarvam Prism evaluation ↗ · Published 3 November 2026.
Average across three decision indices
Index score- Sarvam Prism71.8
- Perplexity Decider v1.268
- Jev 1.1464.5
- Clef62.6
- Microsoft-Decision-161.1
Build with the Sarvam SDK
pip install -U "sarvamai>=0.1.43"V2 · Sarvam SDK · Decisionsimport osfrom sarvamai import SarvamAIclient = SarvamAI(api_subscription_key=os.environ["SARVAM_API_KEY"])response = client.decisions.create(model="sarvam-prism",state="My Stripe integration stopped working and all checkout payments are failing.",questions={"urgent": {"type": "noul","instructions": "Is this urgent and revenue-impacting?"},"department": {"type": "choice","instructions": "Which team should handle this?","criteria": {"billing": "Payments or invoices","technical": "Bugs or outages","sales": "New business enquiries"}},"severity": {"type": "score","instructions": "Rate the severity.","criteria": ["trivial","minor","moderate","major","critical"]}},)department = response.answers["department"]top_probability = department.probabilities[department.choice]if top_probability >= 0.9:print("Route to", department.choice)else:print("Send for review", department.probabilities)
- 01 Install the Sarvam SDK
Install
sarvamai(Python 0.1.43+ or JavaScript 1.1.15+). Store your key inSARVAM_API_KEY. - 02 Call the Decisions API
Send
POST /v2/systemonewith model IDsarvam-prismviaclient.decisions.create. The example sends one state and three typed questions. - 03 Validate your application
Check probabilities and thresholds on representative states. Route confident answers automatically and send uncertain ones to review before production traffic.
Frequently Asked
Questions
Explore other models
View catalogueSarvam 105B
- Sarvam
- Indian languages
- 128K context
Flagship 105B Mixture-of-Experts model trained from scratch for Indian-language understanding, complex reasoning, coding and agentic workflows.
Sarvam 105B Conversations
- Sarvam
- Indian languages
- 32K context
Post-trained variant of Sarvam 105B for real-time dialogue, voice agents and multi-turn conversations across Indian languages.
GLM 5.3
- Z.ai
- Reasoning and coding
- 1M context
Large-scale reasoning model built for complex software engineering and long-horizon agent tasks.
From model choice to production. Bring your workload, traffic expectations and latency targets. Build on Sarvam’s serving stack in India.
From model choice to production.
Bring your workload, traffic expectations and latency targets. Build on Sarvam’s serving stack in India.